io.github.4hmetuyar/agent-graph-auditor

Official registry Maps, travel and weather

Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

NPM package @guardbee/mcp-agent-graph-auditor
Claude Code
claude mcp add agent-graph-auditor -- npx -y @guardbee/mcp-agent-graph-auditor@0.1.2
JSON configuration (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "agent-graph-auditor": {
            "command": "npx",
            "args": [
                "-y",
                "@guardbee/mcp-agent-graph-auditor@0.1.2"
            ]
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. GuardBee MCP
  2. Which package should I use?
  3. Benchmarks
  4. Examples
  5. Packages
  6. Security
  7. Telemetry
  8. Development
  9. Versioning and publishing
  10. Structure
  11. Project history

GuardBee MCP

🇬🇧 English | 🇹🇷 Türkçe | 🇨🇳 中文 | 🇯🇵 日本語 | 🇰🇷 한국어 | 🇧🇷 Português | 🇪🇸 Español | 🇩🇪 Deutsch

Security for AI agents and MCP. GuardBee puts a gateway between your agents and their tools and models that masks personal data and secrets, blocks prompt injection and toxic data flows, asks before risky calls and keeps a tamper-evident audit log, plus scanners that check your code and configs against the OWASP MCP Top 10. Open source (MIT), runs on your machine, no account needed.

# Put your existing MCP servers behind the gateway (backs up your client config first)
npx -y @guardbee/mcp-security-proxy@^1 init --client claude-desktop   # or cursor, claude-code

# Check a codebase against the OWASP MCP Top 10
npx -y @guardbee/mcp-owasp-scan scan . --fail-on=high

Run it yourself: examples/demo (npm install && npm start).

Which package should I use?

You want to…InstallHow
Protect agents at runtime: mask personal data, block injection and toxic flows, approve risky calls, keep an audit log@guardbee/mcp-security-proxyPut it in front of your MCP servers (guardbee-proxy init imports your client config)
Check a codebase against the OWASP MCP Top 10 in one pass, in CI@guardbee/mcp-owasp-scannpx @guardbee/mcp-owasp-scan scan . --format=sarif --fail-on=high
Give an agent many GuardBee checks from one MCP server@guardbee/security-suiteguardbee serve (recommended set), --tools=code,network or all
Find leaked keys in files, git history or agent transcripts@guardbee/mcp-secret-scannernpx @guardbee/mcp-secret-scanner scan . --history
Audit the MCP servers configured on developer machines@guardbee/mcp-config-auditornpx @guardbee/mcp-config-auditor discover
Let an agent query a database without seeing raw personal data@guardbee/mcp-db-gatewayPoint it at your database with a policy
Use the detectors in your own code@guardbee/guard-coreimport { maskPiiInText } from "@guardbee/guard-core"

Every other package is a single check (one OWASP risk, one protocol, one file type); each is in security-suite too. npx @guardbee/security-suite list shows them with what they check.

Benchmarks

Detection is measured, not claimed: packages/pii-bench is a reproducible benchmark for Turkish and international personal data, with bootstrap 95% intervals and the datasets in the repo.

BenchmarkResult
Identifiers (TC Kimlik, IBAN, card, phone, e-mail, …), 400 documents + 160 cleanF1 97.1, recall 100%, false alarms on clean documents 8.1%, 0.04 ms per document
Person names with the optional NER model, same setF1 99.5
Hand-written hard cases for names (tr-names-challenge)F1 97.1, 0 false alarms
KVKK Art. 6 special categories with NER (tr-special-challenge)F1 97.5, 0 false alarms
Bypass suite: 5 identifiers × 16 disguises (base64, hex, URL/HTML/\u escapes, other scripts' digits, separators)80 / 80 masked, 0 of 16 look-alike strings changed

The identifier detectors were tuned after reading this set's misses, so the challenge sets are the fairer measure; the pii-bench README lists the limits. Any other detector can be run on the same data through its System interface.

Examples

Ready-to-copy proxy policies (minimal, KVKK, coding agent, LLM gateway), client configs for Claude Desktop, Claude Code, Cursor and VS Code, and CI templates for GitHub Actions and GitLab: examples/.

Packages

PackagenpmDescription
packages/ai-code-scanner@guardbee/mcp-ai-code-scannerScans a codebase for insecure LLM/AI integration patterns (client-exposed keys, unsafe output handling, excessive agency, PII→prompt, prompt injection)
packages/compliance-checker@guardbee/mcp-compliance-checkerKVKK/GDPR/CCPA compliance checks
packages/dependency-auditor@guardbee/mcp-dependency-auditorCVE scanning for npm/pip/cargo dependencies (OSV)
packages/dns-intelligence@guardbee/mcp-dns-intelligenceDNS record enumeration, misconfiguration and dangling-subdomain detection
packages/db-gateway@guardbee/mcp-db-gatewayKVKK/GDPR-compliant gateway between an LLM and a database (PII masking, RBAC, rate limiting, queryable audit log; Prisma/Postgres/MySQL/SQLite/MongoDB adapters; optional insert/update/delete support)
packages/mcp-server-auditor@guardbee/mcp-server-auditorScans other MCP servers' tool definitions for insecure patterns (excessive agency, shell/eval/SQL/SSRF sinks, loose schemas, hardcoded secrets, wildcard CORS)
packages/prompt-injection-scanner@guardbee/mcp-prompt-injection-scannerScans RAG content/scraped pages for indirect prompt injection (instruction override, spoofed role/chat-template tokens, hidden text, "Dear AI" direct address, data-exfiltration instructions)
packages/llm-redteam@guardbee/mcp-llm-redteamActively red-teams a live LLM endpoint/chatbot with canary-based jailbreak/extraction/obfuscation probes (OpenAI/Anthropic/webhook targets)
packages/model-scanner@guardbee/mcp-model-scannerScans ML model files (PyTorch, pickle, safetensors, Keras/H5, ONNX) for supply-chain risks — dangerous pickle deserialization globals, disguised/malformed safetensors headers, Keras Lambda-layer RCE, ONNX external-data path traversal
packages/vector-store-scanner@guardbee/mcp-vector-store-scannerProbes vector-database endpoints (Weaviate, Qdrant, Chroma, Elasticsearch/OpenSearch, Redis, Postgres/pgvector) for unauthenticated exposure of embeddings and RAG data
packages/prompt-leak-scanner@guardbee/mcp-prompt-leak-scannerCatches leaked credentials and PII (API keys, TC Kimlik No, credit cards, IBANs) in outbound LLM prompts — as MCP scan tools, and as a live reverse proxy in front of a real LLM API
packages/document-scanner@guardbee/mcp-document-scannerFinds PII and credentials inside PDFs, screenshots and scanned documents — PDF text layer plus optional OCR (Turkish and English) — before they reach an LLM
packages/agent-graph-auditor@guardbee/mcp-agent-graph-auditorBuilds a reachability graph across multi-agent orchestration configs (LangGraph, CrewAI, AutoGen/ag2) to find transitive excessive agency — an agent that reaches a dangerous tool only through delegation to another agent
packages/tool-poisoning-scanner@guardbee/mcp-tool-poisoning-scannerScans MCP server tool definitions for tool poisoning (hidden instructions embedded in a tool's description) and confused-deputy mismatches (a read-only-sounding tool whose handler has a shell/eval/file-write/env-dump sink)
packages/rug-pull-detector@guardbee/mcp-rug-pull-detectorConnects live to another MCP server (stdio/HTTP), baselines its tools/list response, and detects an "MCP rug pull" — a tool's description/schema/annotations silently changing after it was already approved
packages/memory-poisoning-scanner@guardbee/mcp-memory-poisoning-scannerScans agent code for memory poisoning — untrusted input written into persistent, cross-session memory (MemGPT-style archival/core memory, or a long-term vector store) that later gets recalled and trusted as context
packages/oauth-auditor@guardbee/mcp-oauth-auditorScans an MCP server's own authorization code for OAuth 2.1 anti-patterns named in the MCP spec's Security Considerations — token passthrough, missing audience validation, OAuth/OIDC discovery SSRF, missing PKCE, loose redirect_uri validation, hardcoded client secrets
packages/elicitation-auditor@guardbee/mcp-elicitation-auditorScans MCP server code for elicitation anti-patterns in the 2026-07-28 spec — form mode asking for secrets or payment data, URL mode pointed straight at a third-party authorize endpoint, credentials or PII embedded in the elicitation URL
packages/toxic-flow-auditor@guardbee/mcp-toxic-flow-auditorAudits an MCP tool catalog for toxic flows (Simon Willison's lethal trifecta) — untrusted content + sensitive/private data + exfiltration or destruction on the same server; A–F grade, KVKK-aware heuristics, OWASP MCP10:2025
packages/audit-gap-auditor@guardbee/mcp-audit-gap-auditorAudits MCP server source for OWASP MCP08:2025 (Lack of Audit and Telemetry) — missing tool-call trails, raw args/results in logs, hard-disabled audit, silent catches, audit events without correlation ids
packages/context-oversharing-auditor@guardbee/mcp-context-oversharing-auditorAudits agent/MCP source for OWASP MCP10:2025 context oversharing — full conversation dumps, unscoped memory tools, shared global session stores, system-prompt leaks via tools, cross-session tool-result bleed, unfiltered vector queries (complements toxic-flow’s catalog trifecta)
packages/owasp-scan@guardbee/mcp-owasp-scanUnified OWASP MCP Top 10 meta-scanner — path orchestration of GuardBee auditors + live/catalog tools/list toxic-flow/poisoning, A–F grade, SARIF; optional MCP09 Shadow MCP discover
packages/mcp-config-auditor@guardbee/mcp-config-auditorAudits MCP client configs (Cursor/Claude/Windsurf/VS Code) and agent SKILL.md for unpinned packages, secrets, wildcard auto-approve, unauthenticated remotes, typosquats, cross-server/skill shadowing; discover finds Shadow MCP (OWASP MCP09) vs an org allowlist
packages/threat-rules@guardbee/mcp-threat-rulesMCP bridge to Agent Threat Rules (ATR) — runtime detection for prompt injection, tool poisoning, and MCP attacks, with GuardBee follow-up scanner hints
packages/a2a-auditor@guardbee/mcp-a2a-auditorScans an agent's Agent2Agent (A2A) protocol implementation (TypeScript and Python) for anti-patterns found in the reference SDKs' own source — unauthenticated push-notification webhook fetches (SSRF), Agent Cards with no authentication requirement, credentials embedded in publicly-served Agent Card metadata
packages/slopsquat-scanner@guardbee/mcp-slopsquat-scannerChecks every dependency declared in a project's own manifest (package.json, requirements.txt, pyproject.toml) against the real npm/PyPI registry — flags names that don't exist at all (likely LLM-hallucinated, i.e. slopsquatting) and names that exist but were only very recently published
packages/unbounded-consumption-auditor@guardbee/mcp-unbounded-consumption-auditorScans LLM/agent application code for Unbounded Consumption ("denial of wallet", OWASP LLM Top 10 2026 #6) — missing output token limits, missing timeouts on hand-rolled LLM HTTP calls, unbounded agent tool-calling/retry loops, explicitly disabled framework safety limits (LangChain max_iterations, openai-agents max_turns), and MCP tool handlers with no visible rate limiting
packages/secret-scanner@guardbee/mcp-secret-scannerScans files for leaked secrets and API keys
packages/security-proxy@guardbee/mcp-security-proxyMCP security gateway: several MCP servers behind one policy, with toxic-flow (lethal trifecta) blocking, approvals, PII masking and a hash-chained audit log
packages/security-suite@guardbee/security-suiteEvery scanner and auditor below from one install: one MCP server with the groups you pick, and a CLI that runs any package
packages/ssl-inspector@guardbee/mcp-ssl-inspectorTLS certificate/cipher/protocol inspection
packages/vulnerability-scanner@guardbee/mcp-vulnerability-scannerTriggers GuardBee scans, queries findings, AI-assisted remediation guidance
packages/guard-core@guardbee/guard-core(internal) Shared detector library — PII/secret masking, prompt injection rules, tool classification; not an MCP server on its own
packages/telemetry@guardbee/mcp-telemetry(internal) Shared usage-telemetry client — not an MCP server on its own

Security

Found a vulnerability? Report it privately: see SECURITY.md. Contributions are welcome: CONTRIBUTING.md.

Telemetry

Packages can send usage telemetry to GuardBee via @guardbee/mcp-telemetry: which tool is called, how often, and how long it takes. It is off by default (opt-in); nothing is sent unless you set GUARDBEE_TELEMETRY=1. When it is on, a one-time notice is printed to stderr on first use.

  • To enable: GUARDBEE_TELEMETRY=1 (or true/on/yes); unset it to turn telemetry off again
  • What's sent: tool name, short (≤40 character) parameter values (e.g. table: "users", limit: 50), success/failure, duration
  • What's NEVER sent: values under keys like content/text/data/filter/password/email/apiKey/token, and any string longer than 40 characters — all replaced with "[redacted: ...]" by redactParams() in packages/telemetry/src/redact.ts. So the full content of scanned files/code, or the real row data from an insert_row/update_row call, is never sent.

Details: packages/telemetry/README.md.

Development

pnpm install
pnpm build     # turbo run build — all packages, in dependency order
pnpm test      # turbo run test

To work on a single package:

pnpm --filter @guardbee/mcp-ssl-inspector dev

Versioning and publishing

Packages are versioned independently (Changesets). If you changed something in a PR:

pnpm changeset

After merging to main, CI automatically opens a version PR; merging that PR publishes the changed packages to npm (see .github/workflows/release.yml).

Stability

Packages at 1.0 or later follow semantic versioning: a breaking change to the CLI, the MCP tool names and parameters, the config format or the exported API comes only with a new major version, and is listed in the package's CHANGELOG.md. New rules and detectors arrive in minor versions; they can report findings an earlier version did not. Packages still at 0.x may change between minor versions.

PackageStable since
@guardbee/mcp-security-proxy1.0
@guardbee/guard-core1.0
@guardbee/mcp-secret-scanner1.0
@guardbee/mcp-prompt-injection-scanner1.0
@guardbee/mcp-prompt-leak-scanner1.0
@guardbee/mcp-toxic-flow-auditor1.0

Structure

  • pnpm workspaces — packages/*, real workspace:* dependencies (e.g. security-suite depends on the other packages directly from the workspace, not a registry version)
  • Turborepo — build/test/type-check pipeline, dependency-graph-aware ordering and caching
  • Shared config — tsconfig.base.json and vitest.shared.ts at the root; each package layers its own settings on top

Project history

The monorepo's earlier write-ups are in CHANGELOG.md; each package's release notes are in its own CHANGELOG.md and on GitHub Releases.

Frequently asked questions

What is io.github.4hmetuyar/agent-graph-auditor?

Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs

How do I install io.github.4hmetuyar/agent-graph-auditor?

It runs on your machine. In Claude Code: claude mcp add agent-graph-auditor -- npx -y @guardbee/mcp-agent-graph-auditor@0.1.2. For other clients, paste the JSON configuration from this page into their MCP settings.

Does io.github.4hmetuyar/agent-graph-auditor need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is io.github.4hmetuyar/agent-graph-auditor open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains io.github.4hmetuyar/agent-graph-auditor?

It is published by GuardBee. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.